SourCoachSauers
commited on
Commit
•
59b04f4
1
Parent(s):
edeee06
color_descriptions
Browse files- README.md +2 -2
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- tokenizer.json +27 -0
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# results
|
18 |
|
19 |
-
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -54,6 +54,6 @@ The following hyperparameters were used during training:
|
|
54 |
|
55 |
- PEFT 0.11.1
|
56 |
- Transformers 4.42.4
|
57 |
-
- Pytorch 2.
|
58 |
- Datasets 2.20.0
|
59 |
- Tokenizers 0.19.1
|
|
|
16 |
|
17 |
# results
|
18 |
|
19 |
+
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on an unknown dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
54 |
|
55 |
- PEFT 0.11.1
|
56 |
- Transformers 4.42.4
|
57 |
+
- Pytorch 2.3.1+cu121
|
58 |
- Datasets 2.20.0
|
59 |
- Tokenizers 0.19.1
|
adapter_config.json
CHANGED
@@ -20,11 +20,11 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"v_proj",
|
25 |
"o_proj",
|
26 |
"gate_proj",
|
27 |
-
"
|
|
|
28 |
],
|
29 |
"task_type": "CAUSAL_LM",
|
30 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"q_proj",
|
|
|
24 |
"o_proj",
|
25 |
"gate_proj",
|
26 |
+
"k_proj",
|
27 |
+
"v_proj"
|
28 |
],
|
29 |
"task_type": "CAUSAL_LM",
|
30 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 57701064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f75b66a4ad11de520f9fa29c2e12fe3b5f3cc284d5aeea05cc10b5ce5a38f60
|
3 |
size 57701064
|
tokenizer.json
CHANGED
@@ -67,6 +67,12 @@
|
|
67 |
"id": "A",
|
68 |
"type_id": 0
|
69 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
}
|
71 |
],
|
72 |
"pair": [
|
@@ -82,6 +88,12 @@
|
|
82 |
"type_id": 0
|
83 |
}
|
84 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
85 |
{
|
86 |
"SpecialToken": {
|
87 |
"id": "<s>",
|
@@ -93,9 +105,24 @@
|
|
93 |
"id": "B",
|
94 |
"type_id": 1
|
95 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
96 |
}
|
97 |
],
|
98 |
"special_tokens": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
99 |
"<s>": {
|
100 |
"id": "<s>",
|
101 |
"ids": [
|
|
|
67 |
"id": "A",
|
68 |
"type_id": 0
|
69 |
}
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"SpecialToken": {
|
73 |
+
"id": "</s>",
|
74 |
+
"type_id": 0
|
75 |
+
}
|
76 |
}
|
77 |
],
|
78 |
"pair": [
|
|
|
88 |
"type_id": 0
|
89 |
}
|
90 |
},
|
91 |
+
{
|
92 |
+
"SpecialToken": {
|
93 |
+
"id": "</s>",
|
94 |
+
"type_id": 0
|
95 |
+
}
|
96 |
+
},
|
97 |
{
|
98 |
"SpecialToken": {
|
99 |
"id": "<s>",
|
|
|
105 |
"id": "B",
|
106 |
"type_id": 1
|
107 |
}
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"SpecialToken": {
|
111 |
+
"id": "</s>",
|
112 |
+
"type_id": 1
|
113 |
+
}
|
114 |
}
|
115 |
],
|
116 |
"special_tokens": {
|
117 |
+
"</s>": {
|
118 |
+
"id": "</s>",
|
119 |
+
"ids": [
|
120 |
+
2
|
121 |
+
],
|
122 |
+
"tokens": [
|
123 |
+
"</s>"
|
124 |
+
]
|
125 |
+
},
|
126 |
"<s>": {
|
127 |
"id": "<s>",
|
128 |
"ids": [
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
-
"add_eos_token":
|
4 |
"add_prefix_space": null,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
+
"add_eos_token": true,
|
4 |
"add_prefix_space": null,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be4fc7fe27d03f5ac19bd26ea384499bf452563447f251672b9bb0243ad7f003
|
3 |
size 5368
|